← All models

ElevenLabs Eleven v3

Audio Available Full comparison ↗

elevenlabs/eleven-v3 · by ElevenLabs · neural-tts

Pricing — 1 offering(s)

ElevenLabs

Text characters

  • $100.00 / 1M characters Historical 2026-07-30 → 2026-09-29
    ElevenLabs' dedicated API pricing page lists "Multilingual v2 / v3" as one combined row at $0.10 per 1K…

    ElevenLabs' dedicated API pricing page lists "Multilingual v2 / v3" as one combined row at $0.10 per 1K characters ($100/1M) — v3 is priced identically to Multilingual v2 on the pay-as-you-go API, not separately broken out. effective_from is the date this entry was sourced, not a confirmed price-change date.

  • $80.00 / 1M characters Current 2026-09-30 → present
    SCO-672: elevenlabs.io/pricing/api now lists "v3" at $0.08 per 1K characters ($80/1M). That's the list price…

    SCO-672: elevenlabs.io/pricing/api now lists "v3" at $0.08 per 1K characters ($80/1M). That's the list price: this card has no promo tag and no struck price (only v4 and v4 Turbo carry the "72% off until Oct 12" promo). SCO-346 read $0.10 per 1K from the same page on 2026-07-30, so ElevenLabs cut the rate between those dates. The exact change date is unknown (no archived snapshot was reachable), so effective_from is the date this was verified.

Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.

See how ElevenLabs Eleven v3 fits into a cost-aware routing setup

See how →

Capability profile

How ElevenLabs Eleven v3 rates across core capability dimensions, with the task-level evidence behind each rating.

voice naturalness Strong

ElevenLabs' most expressive model — Audio Tags ([excited], [whispers], [sighs], etc.) give fine-grained emotional/delivery control beyond Multilingual v2's baseline. ElevenLabs' own GA testing reports a 68% error-rate reduction (15.3% to 4.9%) on numbers, symbols, and specialised notation across 8 languages vs the alpha release.

language support Strong

70+ languages per ElevenLabs' own v3 page — more than double Multilingual v2's 29.

voice variety Strong

Same 5,000+ voice library as Multilingual v2, plus a dialogue mode that weaves multiple voices into one multi-speaker generation, matching prosody and emotional range across speakers.

streaming latency Moderate

No latency figures published specific to v3 — not vendor-confirmed. Inferred comparable to Multilingual v2 (~400ms first-byte) as the shared base model; Audio Tags and dialogue-mode processing add overhead, so v3 is unlikely to be faster.

cloning support Strong

Full ElevenLabs voice cloning, same as Multilingual v2 and Flash v2.5.

Benchmarks

Benchmark Score Config Source
Pronunciation/notation accuracy improvement vs Eleven v3 alpha (vendor-reported) 68 % Error rate reduced from 15.3% to 4.9% across 27 categories (currency, chemical formulas, sports scores, phone numbers, etc.) in 8 languages, per ElevenLabs' own GA announcement. Not independently verified. source ↗

Operator guidance

Choose Eleven v3 over Multilingual v2 when a script needs explicit emotional/delivery direction (Audio Tags) or multi-speaker dialogue — neither of which Multilingual v2 supports, at the same $80/1M-character price (SCO-672). Eleven v4 (2026-09-28) now supersedes v3 at the same list price (SCO-670). Route latency-sensitive, real-time applications to Flash v2.5 instead; v3's audio-tag and dialogue features are not oriented toward low-latency streaming.

Use cases

Limitations

Citations